sharkdp/hexyl | ProgramBench

A command-line hex viewer

906

Generated Behavioral Tests

100.0%

Best Score

Muse Wonder Full

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

30 runs

#	Model	Score	Cost	Calls
1	Muse Wonder Full	100.0%	TBA	233	trace →
2	Claude Opus 5 (xhigh)	99.7%	$37.26	242	trace →
3	GPT 6 Astra (max)	99.4%	$9.39	48	trace →
4	Claude Opus 5.5 (xhigh)	99.3%	$13.56	198	trace →
5	Muse Wonder (xhigh)	99.3%	$22.06	296	trace →
6	Claude Fable 5.1 (xhigh)	99.0%	$32.37	233	trace →
7	GPT-5.6 Sol (xhigh)	95.9%	$5.82	33	trace →
8	Claude Opus 4.8 (xhigh)	95.7%	$24.50	157	trace →
9	GPT 5.5 (xhigh)	95.4%	$13.44	87	trace →
10	Gemini 3.7 Flash	94.0%	$2.19	144	trace →
11	Muse Spark 1.2 (xhigh)	91.7%	$3.49	231	trace →
12	Claude Opus 4.7 (xhigh)	89.3%	$23.56	256	trace →
13	Gemini 3.5 Flash	87.2%	$10.51	188	trace →
14	Muse Spark 1.1 (xhigh)	84.7%	$0.46	356	trace →
15	GLM-5.2	82.9%	$11.68	123	trace →
16	Claude Sonnet 4.6	82.8%	$32.57	443	trace →
17	GPT-5.6 Sol	82.2%	$1.24	22	trace →
18	Claude Opus 4.7	81.6%	$10.35	164	trace →
19	Claude Opus 4.6	81.3%	$12.37	236	trace →
20	Gemini 3.6 Flash	76.6%	$4.79	129	trace →
21	GPT 5.4	54.1%	$0.32	12	trace →
22	Gemini 3 Flash	51.9%	$0.45	76	trace →
23	GPT 5.5 (high)	50.7%	$3.22	33	trace →
24	GPT 5.5	45.1%	$1.07	14	trace →
25	Gemini 3.1 Pro	36.0%	$2.46	122	trace →
26	Claude Haiku 4.5	34.1%	$0.87	92	trace →
27	Muse Spark 1.3 (max)	22.7%	$6.65	286	trace →
28	GPT 5 mini	7.3%	$0.02	13	trace →
29	Muse Spark 1.3 (xhigh)	4.4%	$2.62	295	trace →
30	GPT 5.4 mini	0.0%	$0.04	9	trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run